Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.
Python agent-evaluationagent-pluginsagent-securityagent-skillsagentic-aibenchmarkci-templatesclaude-codecodexevaluateevaluationharnesspluginplugin-evaluationsecurity-scannerskill-evalskill-evaluationskill-evaluatorskill-gap-analysisskills
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
"""Validated resource limits for inter-skill similarity scans."""
from skillevaluator.constants import SIMILARITY_MAX_ENTRIES
def validate_max_entries(max_entries: int) -> None:
if type(max_entries) is not int or not 1 <= max_entries <= SIMILARITY_MAX_ENTRIES:
raise ValueError(f"max_entries (--max-entries) must be an integer from 1 to {SIMILARITY_MAX_ENTRIES}")
def validate_max_scalar_comparisons(max_scalar_comparisons: int) -> None:
if type(max_scalar_comparisons) is not int or max_scalar_comparisons < 1:
raise ValueError("max_scalar_comparisons (--max-scalar-comparisons) must be a positive integer")